
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.9)
=> Add worker SGDMWorker(index=1, momentum=0.9)
=> Add worker SGDMWorker(index=2, momentum=0.9)
=> Add worker SGDMWorker(index=3, momentum=0.9)
=> Add worker SGDMWorker(index=4, momentum=0.9)
=> Add worker SGDMWorker(index=5, momentum=0.9)
=> Add worker SGDMWorker(index=6, momentum=0.9)
=> Add worker SGDMWorker(index=7, momentum=0.9)
=> Add worker SGDMWorker(index=8, momentum=0.9)
=> Add worker SGDMWorker(index=9, momentum=0.9)
=> Add worker SGDMWorker(index=10, momentum=0.9)
=> Add worker SGDMWorker(index=11, momentum=0.9)
=> Add worker SGDMWorker(index=12, momentum=0.9)
=> Add worker SGDMWorker(index=13, momentum=0.9)
=> Add worker SGDMWorker(index=14, momentum=0.9)
=> Add worker SGDMWorker(index=15, momentum=0.9)
=> Add worker SGDMWorker(index=16, momentum=0.9)
=> Add worker SGDMWorker(index=17, momentum=0.9)
=> Add worker SGDMWorker(index=18, momentum=0.9)
=> Add worker SGDMWorker(index=19, momentum=0.9)
=> Add worker ByzantineWorker(index=20)
=> Add worker ByzantineWorker(index=21)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fb4b7a772e0>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')
Worker 20 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 21 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 2.1256 top1= 32.9688
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.7706 top1= 52.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1821 top1= 77.8345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1716 top1= 79.3369


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2008 top1= 75.3706

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 1.2558 top1= 65.3125
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.9599 top1= 72.5000
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.8003 top1= 75.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5283 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5180 top1= 87.6302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5416 top1= 87.1294

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.6433 top1= 79.8438
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.6293 top1= 79.0625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.5532 top1= 81.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3963 top1= 89.3630


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3946 top1= 89.4231


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4019 top1= 89.1126

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.4601 top1= 86.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.4372 top1= 87.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.4723 top1= 84.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3411 top1= 90.4948


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3443 top1= 90.3646


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3433 top1= 90.4447

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.3930 top1= 88.2812
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.3677 top1= 88.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.3895 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3117 top1= 91.2861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3126 top1= 91.1458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3123 top1= 91.2159

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.3148 top1= 90.4688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.3237 top1= 90.3125
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.3619 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2857 top1= 91.8369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2874 top1= 91.7368


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2864 top1= 91.8570

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.2794 top1= 91.4062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.3060 top1= 91.2500
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.3114 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2704 top1= 92.2075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2721 top1= 92.1575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2718 top1= 92.1174

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.2671 top1= 92.3438
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.2635 top1= 91.8750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.2971 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2542 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2561 top1= 92.6082


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2549 top1= 92.7284

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.2487 top1= 92.9688
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.2444 top1= 93.1250
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.2735 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2392 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2393 top1= 92.9988


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2412 top1= 92.9888

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.2321 top1= 93.2812
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.2206 top1= 93.7500
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.2363 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2274 top1= 93.3093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2298 top1= 93.2492


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2276 top1= 93.3994

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.2071 top1= 93.7500
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1941 top1= 94.2188
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.2306 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2167 top1= 93.6899


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2187 top1= 93.5196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2209 top1= 93.4796

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.2118 top1= 93.9062
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1903 top1= 94.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.2081 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2068 top1= 93.9203


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2090 top1= 93.9303


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2070 top1= 93.9804

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1789 top1= 94.6875
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1862 top1= 94.2188
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.2077 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1990 top1= 94.1807


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2028 top1= 94.0104


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1983 top1= 94.2909

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1580 top1= 95.4688
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1725 top1= 94.2188
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1753 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1932 top1= 94.2909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1925 top1= 94.2508


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1966 top1= 94.3309

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1553 top1= 96.0938
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1643 top1= 95.3125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1741 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1867 top1= 94.4912


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1887 top1= 94.4010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1875 top1= 94.4010

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1525 top1= 96.0938
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1485 top1= 96.2500
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1549 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1792 top1= 94.5813


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1825 top1= 94.4211


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1787 top1= 94.6414

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1303 top1= 96.8750
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1176 top1= 97.1875
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1519 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1736 top1= 94.8117


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1753 top1= 94.8017


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1753 top1= 94.7817

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1599 top1= 95.1562
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1312 top1= 96.5625
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1396 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1684 top1= 94.9619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1699 top1= 94.8017


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1694 top1= 94.9219

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1247 top1= 97.0312
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1228 top1= 96.5625
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1251 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1626 top1= 95.0421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1645 top1= 94.9720


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1638 top1= 94.9619

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1073 top1= 97.5000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1124 top1= 96.4062
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1123 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1605 top1= 95.0421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1628 top1= 95.0120


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1606 top1= 95.0921

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1158 top1= 97.0312
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1037 top1= 96.8750
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1220 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1537 top1= 95.3125


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1569 top1= 95.2023


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1544 top1= 95.3926

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1190 top1= 97.0312
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0943 top1= 97.5000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1146 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1515 top1= 95.3726


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1550 top1= 95.1623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1517 top1= 95.2724

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0997 top1= 97.5000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0848 top1= 97.0312
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0969 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1483 top1= 95.4327


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1500 top1= 95.4026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1494 top1= 95.4227

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0903 top1= 98.2812
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0939 top1= 97.6562
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0981 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1446 top1= 95.6130


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1460 top1= 95.5329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1457 top1= 95.5028

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1053 top1= 97.3438
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0837 top1= 97.9688
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0949 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1405 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1430 top1= 95.5929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1404 top1= 95.6330

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0783 top1= 98.2812
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0673 top1= 97.9688
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0763 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1380 top1= 95.7632


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1407 top1= 95.6230


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1379 top1= 95.6931

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0904 top1= 97.8125
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0787 top1= 97.8125
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0911 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1348 top1= 95.8433


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1360 top1= 95.8133


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1358 top1= 95.8333

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0794 top1= 98.2812
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0697 top1= 98.1250
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0806 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1316 top1= 95.8233


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1338 top1= 95.7933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1312 top1= 95.9135

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0516 top1= 99.5312
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0421 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0518 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1311 top1= 96.0036


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1341 top1= 95.9435


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1313 top1= 95.9135

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0940 top1= 97.6562
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0958 top1= 97.1875
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0720 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1291 top1= 96.0036


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1316 top1= 95.9235


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1283 top1= 96.0136

